Mapping Maize Area in Heterogeneous Agricultural Landscape with Multi-Temporal Sentinel-1 and Sentinel-2 Images Based on Random Forest

Abstract

Accurate estimation of crop area is essential to adjusting the regional crop planting structure and the rational planning of water resources. However, it is quite challenging to map crops accurately by high-resolution remote sensing images because of the ecological gradient and ecological convergence between crops and non-crops. The purpose of this study is to explore the combining application of high-resolution multi-temporal Sentinel-1 (S1) radar backscatter and Sentinel-2 (S2) optical reflectance images for maize mapping in highly complex and heterogeneous landscapes in the middle reaches of Heihe River, northwest China. We proposed a new two-step method of vegetation extraction and followed by maize extraction, that is, extract the vegetation-covered areas first to reduce the inter-class variance by using a Random Forest (RF) classifier based on S2 data, and then extract the maize distribution in the vegetation area by using another RF classifier based on S1 and/or S2 data. The results demonstrate that the vegetation extraction classifier successfully identified vegetation-covered regions with an overall accuracy above 96% in the study area, and the accuracy of the maize extraction classifier constructed by the combined multi-temporal S1 and S2 images is significantly improved compared with that S1 (alone) or S2 (alone), with an overall accuracy of 87.63%, F1_Score of 0.86, and Kappa coefficient of 0.75. In addition, with the introduction of multi-temporal S1 and/or S2 images in crop growing season, the constructed RF model is more beneficial to maize mapping.

Improving Land Use/Cover Classification Accuracy from Random Forest Feature Importance Selection Based on Synergistic Use of Sentinel Data and Digital Elevation Model in Agriculturally Dominated Landscape

“…Van Tricht, Gobin, Gilliams, and Piccard [63] demonstrate the importance of choosing phenological cycles for crop mapping based on the synergy between the sentinel-1 and -2 data using an RF classifier for increasing model performance. Similarly, many studies demonstrated the importance of Sentinel-1 and -2 for rice mapping in a lowland area [76], mapping paddy rice [77], and mapping Maize Areas in heterogeneous agriculture [78] based on RF. By understanding this trade-off, the current study can help in the selection of datasets and periods for LULC classification with specific applications to agricultural landscapes in semi-arid regions.…”

A new method for classifying maize by combining the phenological information of multiple satellite-based spectral bands

“…Therefore, it is quite difficult to map maize relying on a single band or index due to spectral confusion in summer crops. Even when two or more bands and indexes are input for training, phenological characteristics cannot be extracted effectively (Abubakar et al, 2020;You and Dong, 2020;Chen Y. et al, 2021). Previous methods usually used machine learning Frontiers in Environmental Science frontiersin.org methods, and limited the application capability to the other regions (Rodriguez-Galiano et al, 2012).…”

Mapping Crop Distribution Patterns and Changes in China from 2000 to 2015 by Fusing Remote-Sensing, Statistics, and Knowledge-Based Crop Phenology

“…Using low-medium resolution data, such as MODIS data, or using moderate resolution data, such as Landsat and Sentinel, for crop types that were successfully identified by remote sensing data at the regional or national scale are mainly concentrated on some major crops with large planting areas, for example, rice [25][26][27], wheat [28], maize [29], soybean [30], and sugarcane [31], and mostly different combinations of these crops [32][33][34][35]. Crops with low popularity are generally not included due to their lower visibility on the signals from remote sensing images.…”